RIFi:Robust and iterative indoor localization based on Wi-Fi RSS fingerprints  

作　　者：Wei Liu Meng Niu Yunghsiang S.Han 

机构地区：[1]Schools of Telecommunications Engineering,Xidian University,Xi'an 710071,China [2]Shenzhen Institute for Advanced Study,University of Electronic Science and Technology of China,ShenZhen 518110,China

出　　处：《Journal of Information and Intelligence》2025年第1期1-18,共18页信息与智能学报(英文)

基　　金：supported by the Key Research and Development Program of Shaanxi under Grant(2017DCXL-GY-04-02).

摘　　要：RSS fingerprint based indoor localization consists of two phases:offline phase and online phase.A RSS fingerprint database constructed at the offline phase may be outdated for online phase,which may significantly degrade the localization performance.Furthermore,maintaining an RSS fingerprint database is a labor intensive and time-consuming task.In this paper,we proposes a robust and iterative indoor localization algorithm based on Wi-Fi RSS fingerprints,referred to as RIFi,which does not need to update the RSS fingerprint database and perform well even if the RSS fingerprint database is outdated.Specifically,we demonstrate that smaller localization area can provides better performance for outdated fingerprint database.Furthermore,we propose an iterative algorithm to determine the smaller localization area.Finally,the K-nearest neighbors(KNN)algorithm is invoked for the determined smaller localization area.Simulation results show that the proposed RIFi algorithm can significantly outperforms the traditional KNN algorithm for outdated RSS fingerprint database,and is more robust.

关 键 词：RIFi FINGERPRINT Indoor localization Outdated RSS Smaller localization area 

分 类 号：TN92[电子电信—通信与信息系统]